papers AI Learner
The Github is limit! Click to go to the new site.

Defeats GAN: A Simpler Model Outperforms in Knowledge Representation Learning


Abstract

The goal of knowledge representation learning is to embed entities and relations into a low-dimensional, continuous vector space. How to push a model to its limit and obtain better results is of great significance in knowledge graph’s applications. We propose a simple and elegant method, Trans-DLR, whose main idea is dynamic learning rate control during training. Our method achieves remarkable improvement, compared with recent GAN-based method. Moreover, we introduce a new negative sampling trick which corrupts not only entities, but also relations, in different probabilities. We also develop an efficient way, which fully utilizes multiprocessing and parallel computing, to speed up evaluation of the model in link prediction tasks. Experiments show that our method is effective.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.01777

PDF

http://arxiv.org/pdf/1904.01777


Similar Posts

Comments